The analytical study of a large scale nonlinear neural network is an uneasy *** try to analyze the function of neural systems by probing into the fuzzy logical framework of the neural ceUs'dynamical *** papers inv...
详细信息
ISBN:
(纸本)0780394224
The analytical study of a large scale nonlinear neural network is an uneasy *** try to analyze the function of neural systems by probing into the fuzzy logical framework of the neural ceUs'dynamical *** papers investigate the relation between fuzzy logic and neural *** most investigations focus on finding new function of neural system by combining fuzzy logical and neural system. In this paper,a novel approach is used to understand the nonlinear dynamic characteristics of neural system by analyzing the fuzzy logic framework of neural *** is the only way to understand the behavior of a large scale nonlinear neural *** abstracting the fuzzy logical framework of a neural cell,our analysis enables the delicate design of network *** an example,a difficulty task to build a recurrent network model of primary visual cortex by common dynamical analysis can be easily completed by this kind approach.
The theory of granule computing based on the quotient space is one of the three main granule computing theories. The emphasis is on the structure of the quotient space theory in this paper. Comparing with Rough Set th...
详细信息
Quotient space theory of problem solving, a formal model of granular computing, is generalized in the sense that topological structure is replaced by Cech's closure space. Some basic issues of granular computing, ...
详细信息
NKI contains a multi-domain oriented and large scale knowledge base. Text corpus is an important knowledge source of it. This paper presents an ontology-driven and integrated multi-agent architecture (MAKAT) for achie...
详细信息
Based on Jordan curve theorem, a universal classification method based on hyper surface is recently put forward. The experiments show that the new method can efficiently and accurately classify large data size up to 1...
详细信息
In this paper, a new image classification method is developed. This approach applies graph decomposition and probabilistic neural networks (PNN) to the task of supervised image classification. We use relational graphs...
详细信息
In this paper, a new image classification method is developed. This approach applies graph decomposition and probabilistic neural networks (PNN) to the task of supervised image classification. We use relational graphs to represent image. These graphs are constructed from the feature points of images. Spectra of these graphs are obtained as feature vectors for classification. PNN is adopted to classify image according to the feature vectors. Experimental results show that this method can achieve best result of images classification.
Two algorithms for the phase retrieval of hard X-ray in-line phase contrast imaging are presented. One is referred to as Iterative Angular Spectrum Algorithm (IASA) and the other is a hybrid algorithm that combines IA...
详细信息
Two algorithms for the phase retrieval of hard X-ray in-line phase contrast imaging are presented. One is referred to as Iterative Angular Spectrum Algorithm (IASA) and the other is a hybrid algorithm that combines IASA with TIE (transport of intensity equation). The calculations of the algorithms are based on free space propagation of the angular spectrum. The new approaches are demonstrated with numerical simulations. Comparisons with other phase retrieval algorithms are also performed. It is shown that the phase retrieval method combining the IASA and TIE is a promising technique for the application of hard X-ray phase contrast imaging.
In this paper, we propose a dimension reduction method of locality preserving projections based on QR-decomposition of training data matrix, namely LPP/QR. It is efficient and effective in under-sampled recognition of...
详细信息
In this paper, we propose a dimension reduction method of locality preserving projections based on QR-decomposition of training data matrix, namely LPP/QR. It is efficient and effective in under-sampled recognition of image and text data, especially when the number of dimension of data is greater than the number of training samples. Its theoretical foundation is presented. The equivalence between LPP/QR and generalized LPP is induced although LPP/QR is faster than generalized LPP. Several experiments are conducted on Yale face database. High recognition rates show that the algorithm performs better in under-sampled situations.
The theory of granule computing based on the quotient space is one of the three main granule computing theories. The emphasis is on the structure of the quotient space theory in this paper. Comparing with rough set th...
详细信息
The theory of granule computing based on the quotient space is one of the three main granule computing theories. The emphasis is on the structure of the quotient space theory in this paper. Comparing with rough set theory, the authors point out the importance of the structure in granule computing theory. A new method of constructing quotient space according to the structure is also presented in this paper. The differences between the quotient structure and structure-based method are proved. Finally, some examples show the rationality and feasibility of our methods.
A online infomax algorithm is proposed in this paper. The performances and properties of this online algorithm is investigated in detail. To the problem of the artifacts removal in real life EEG signal, both the onlin...
详细信息
暂无评论